SP

Spark 270M FP16

SparkGGUF by TitleOSUpdated 2025-12-17
Download on Hugging Face
Parameters268M
Context32K
Layers18
Architecturegemma3
Smallest quant0.3 GB
Quick answer

Spark 270M FP16 needs about 0.9 GB of memory at Q8_0 (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.6 GB.

Spark 270M FP16 is a 268M-parameter Spark model in GGUF format, quantized by TitleOS. Its trained context length is 32K tokens. The repository has 1 quant file, from 0.3 GB (Q8_0) to 0.3 GB (Q8_0).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_00.3 GB 0.9 GB
Fits Get file →

What GPU do you need for Spark 270M FP16?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q8_0 (0.3 GB file, about 0.9 GB in use).

Which Spark 270M FP16 quant should you choose?

Q8_0 (0.3 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegemma3
Parameters268M
Layers18
Trained context32,768 tokens
KV cache (fp16)18 KB per token

Source

Quantized byTitleOS
FamilySpark
Licensempl-2.0
Downloads (HF)63
Last updated2025-12-17

Frequently asked questions about Spark 270M FP16

How much VRAM does Spark 270M FP16 need?

About 0.9 GB at Q8_0 with an 8K context window. That is the 0.3 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Spark 270M FP16 on an 8 GB GPU?

Yes, with Q8_0: the 0.3 GB file needs about 0.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Spark 270M FP16 GGUF?

It depends on the quant: Q8_0 is 0.3 GB.

What context length does Spark 270M FP16 support?

The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.6 GB at 32K.

Where can I download Spark 270M FP16 GGUF?

The files are on Hugging Face in the TitleOS/Spark-270M-FP16-Q8_0-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Spark 270M FP16 use?

Hugging Face lists the license as mpl-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Spark-270M-FP16

Similar models

Browse all →

More from TitleOS

All by TitleOS →

More Spark models

All Spark →

Other tiny models

All tiny models →